Computer scientists quantify elements of writing style that differentiate successful fiction

Posted on January 10, 2014
Computer scientists quantify elements of writing style that differentiate successful fiction

Dr. Choi and her colleagues in the College of Engineering and Applied Sciences—Vikas Ashok, a teaching assistant in the Department of Computer Science, and Song Feng, a fifth year PhD student in the same department.
Imagine the challenge publishers face, pouring over thousands of manuscripts to determine if a book will be a hit. Stony Brook Department of Computer Science Assistant Professor Yejin Choi thinks she has a tool to bring some science to that art, and she is co-author of a paper, Success with Style: Using Writing Style to Predict the Success of Novels, which was unveiled at the conference on Empirical Methods in Natural Language Processing (EMNLP) 2013.

“Predicting the success of literary works poses a massive dilemma for publishers and aspiring writers alike,” Choi said. “We examined the quantitative connection between writing style and successful literature. Based on novels across different genres, we investigated the predictive power of statistical stylometry in discriminating successful literary works, and identified the stylistic elements that are more prominent in successful writings.”

Statistical stylometry is the statistical analysis of variations in literary style between one writer or genre and another. The study reports, for the first time, that the discipline can be effective in distinguishing highly successful literature from its less successful counterpart, achieving accuracy rates as high as 84%.

Read more at: Phys.org